© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157402
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    я
    1.16
     arabe
    1.03
    ש
    0.96
     ayant
    0.91
     appareils
    0.90
     équipé
    0.89
     entraî
    0.88
     environnement
    0.86
     œufs
    0.86
     équip
    0.86
    POSITIVE LOGITS
    f
    1.33
    are
    1.31
     a
    1.08
    ao
    1.07
    。
    1.05
    g
    1.02
    ala
    0.96
    ong
    0.95
    ।
    0.95
    art
    0.95
    Activations Density 0.000%

    No Known Activations